Shape-Based Human Detection and Segmentation via Hierarchical Part-Template Matching

We propose a shape-based, hierarchical part-template matching approach to simultaneous human detection and segmentation combining local part-based and global shape-template-based schemes. The approach relies on the key idea of matching a part-template tree to images hierarchically to detect humans a...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2010-04, Vol.32 (4), p.604-618
Hauptverfasser:	Zhe Lin, Davis, L.S.
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Artificial Intelligence Biological system modeling Computer vision Crowding Decision Trees Deformable models Detectors Feature extraction Generic human detector hierarchical part-template matching Human Humans Image Processing, Computer-Assisted - methods Image segmentation Iterative methods Matching occlusion analysis part-template tree Pattern Recognition, Automated - methods pose-adaptive descriptor Posture - physiology Robustness Segmentation Shape Training data Trees
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!